Join us
Anthropic
15 posts

Anthropic

Latest posts
01 Anthropic
Many-Shot Jailbreaking: A New Vulnerability in LLMs
Many-Shot Jailbreaking: A New Vulnerability in LLMs

Long context LLMs vulnerable to "many-shot jailbreaking." Faux dialogues override safety training. Mitigation efforts ongoing but challenging.

by AI-360
Your link has expired. Please request a new one.
Your link has expired. Please request a new one.
Your link has expired. Please request a new one.
Great! You've successfully signed up.
Great! You've successfully signed up.
Welcome back! You've successfully signed in.
Success! You now have access to additional content.